© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11339
    Prev
    Next
    INDEX
    Explanations

    numbers and sequences associated with legal or regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Citations to U.S. Supreme Court cases

    np_acts-logits-general · gemini-2.0-flash

    legal citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.78
    EndGlobalSection
    -0.70
     صوتيه
    -0.69
     cref
    -0.65
    日閲覧
    -0.65
    EnableWeb
    -0.64
    onViewCreated
    -0.64
    contentLoaded
    -0.63
    alic
    -0.63
    migrationBuilder
    -0.62
    POSITIVE LOGITS
    FieldDescriptor
    0.45
    ArgumentParser
    0.44
    níky
    0.42
    ễn
    0.42
    ైన
    0.42
     Beam
    0.42
     Daar
    0.42
     đèn
    0.41
    JNIEnv
    0.40
     unaware
    0.40
    Activations Density 0.145%

    No Known Activations